LHM++: An Efficient Large Human Reconstruction Model for Pose-free Images to 3D

TL;DR

LHM++ is a fast, efficient model that reconstructs high-quality, animatable 3D human avatars from casual, pose-free images using a novel transformer architecture and real-time rendering refinement.

Contribution

The paper introduces LHM++, a large-scale human reconstruction model that operates without camera or pose data, utilizing a transformer-based architecture for detailed 3D avatar generation.

Findings

Produces high-fidelity 3D humans from pose-free images

Operates in seconds with real-time rendering

Outperforms existing methods in visual quality and efficiency

Abstract

Reconstructing animatable 3D humans from casually captured images of articulated subjects without camera or pose information is highly practical but remains challenging due to view misalignment, occlusions, and the absence of structural priors. In this work, we present LHM++, an efficient large-scale human reconstruction model that generates high-quality, animatable 3D avatars within seconds from one or multiple pose-free images. At its core is an Encoder-Decoder Point-Image Transformer architecture that progressively encodes and decodes 3D geometric point features to improve efficiency, while fusing hierarchical 3D point features with image features through multimodal attention. The fused features are decoded into 3D Gaussian splats to recover detailed geometry and appearance. To further enhance visual fidelity, we introduce a lightweight 3D-aware neural animation renderer that refines the rendering quality of reconstructed avatars in real time. Extensive experiments show that our method produces high-fidelity, animatable 3D humans without requiring camera or pose annotations. Our code and project page are available at https://lingtengqiu.github.io/LHM++/